Hugging Face's logo

farid1088
/
GQA_RoBERTa_legal_SQuAD_complete_augmented_100

Question Answering
Transformers
TensorBoard
Safetensors
roberta
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
farid1088 commited on
Commit
c819ac2
路
verified 路
1 Parent(s): 651f800

Model save

Browse files
Files changed (11) hide show
  1. README.md +154 -0
  2. config.json +27 -0
  3. emissions.csv +2 -0
  4. merges.txt +0 -0
  5. model.safetensors +3 -0
  6. runs/Mar06_02-01-35_hcdsgpu2/events.out.tfevents.1709690501.hcdsgpu2.586318.0 +3 -0
  7. special_tokens_map.json +51 -0
  8. tokenizer.json +0 -0
  9. tokenizer_config.json +64 -0
  10. training_args.bin +3 -0
  11. vocab.json +0 -0
README.md ADDED
@@ -0,0 +1,154 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ model-index:
5
+ - name: GQA_RoBERTa_legal_SQuAD_complete_augmented_100
6
+ results: []
7
+ ---
8
+
9
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
10
+ should probably proofread and complete it, then remove this comment. -->
11
+
12
+ # GQA_RoBERTa_legal_SQuAD_complete_augmented_100
13
+
14
+ This model was trained from scratch on the None dataset.
15
+ It achieves the following results on the evaluation set:
16
+ - Loss: 3.7135
17
+
18
+ ## Model description
19
+
20
+ More information needed
21
+
22
+ ## Intended uses & limitations
23
+
24
+ More information needed
25
+
26
+ ## Training and evaluation data
27
+
28
+ More information needed
29
+
30
+ ## Training procedure
31
+
32
+ ### Training hyperparameters
33
+
34
+ The following hyperparameters were used during training:
35
+ - learning_rate: 2e-05
36
+ - train_batch_size: 128
37
+ - eval_batch_size: 32
38
+ - seed: 42
39
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
40
+ - lr_scheduler_type: linear
41
+ - num_epochs: 100
42
+
43
+ ### Training results
44
+
45
+ | Training Loss | Epoch | Step | Validation Loss |
46
+ |:-------------:|:-----:|:----:|:---------------:|
47
+ | No log | 1.0 | 4 | 5.0223 |
48
+ | No log | 2.0 | 8 | 2.8588 |
49
+ | No log | 3.0 | 12 | 3.7945 |
50
+ | No log | 4.0 | 16 | 2.6351 |
51
+ | No log | 5.0 | 20 | 3.0764 |
52
+ | No log | 6.0 | 24 | 2.4511 |
53
+ | No log | 7.0 | 28 | 2.5440 |
54
+ | No log | 8.0 | 32 | 2.8751 |
55
+ | No log | 9.0 | 36 | 2.6175 |
56
+ | No log | 10.0 | 40 | 2.9249 |
57
+ | No log | 11.0 | 44 | 2.3475 |
58
+ | No log | 12.0 | 48 | 2.8935 |
59
+ | No log | 13.0 | 52 | 2.7712 |
60
+ | No log | 14.0 | 56 | 2.5911 |
61
+ | No log | 15.0 | 60 | 3.1567 |
62
+ | No log | 16.0 | 64 | 2.7002 |
63
+ | No log | 17.0 | 68 | 3.0797 |
64
+ | No log | 18.0 | 72 | 2.9672 |
65
+ | No log | 19.0 | 76 | 3.2383 |
66
+ | No log | 20.0 | 80 | 3.1447 |
67
+ | No log | 21.0 | 84 | 3.1826 |
68
+ | No log | 22.0 | 88 | 3.4054 |
69
+ | No log | 23.0 | 92 | 3.1397 |
70
+ | No log | 24.0 | 96 | 3.3258 |
71
+ | No log | 25.0 | 100 | 3.2254 |
72
+ | No log | 26.0 | 104 | 3.1559 |
73
+ | No log | 27.0 | 108 | 3.5900 |
74
+ | No log | 28.0 | 112 | 3.3985 |
75
+ | No log | 29.0 | 116 | 3.7034 |
76
+ | No log | 30.0 | 120 | 3.6305 |
77
+ | No log | 31.0 | 124 | 3.4161 |
78
+ | No log | 32.0 | 128 | 3.6157 |
79
+ | No log | 33.0 | 132 | 3.3394 |
80
+ | No log | 34.0 | 136 | 3.5239 |
81
+ | No log | 35.0 | 140 | 3.4075 |
82
+ | No log | 36.0 | 144 | 3.3560 |
83
+ | No log | 37.0 | 148 | 3.6675 |
84
+ | No log | 38.0 | 152 | 3.3822 |
85
+ | No log | 39.0 | 156 | 3.5903 |
86
+ | No log | 40.0 | 160 | 3.7123 |
87
+ | No log | 41.0 | 164 | 3.5195 |
88
+ | No log | 42.0 | 168 | 3.6451 |
89
+ | No log | 43.0 | 172 | 3.4411 |
90
+ | No log | 44.0 | 176 | 3.6223 |
91
+ | No log | 45.0 | 180 | 3.4833 |
92
+ | No log | 46.0 | 184 | 3.7552 |
93
+ | No log | 47.0 | 188 | 3.5525 |
94
+ | No log | 48.0 | 192 | 3.7382 |
95
+ | No log | 49.0 | 196 | 3.6046 |
96
+ | No log | 50.0 | 200 | 3.6106 |
97
+ | No log | 51.0 | 204 | 3.6298 |
98
+ | No log | 52.0 | 208 | 3.7597 |
99
+ | No log | 53.0 | 212 | 3.5995 |
100
+ | No log | 54.0 | 216 | 3.6429 |
101
+ | No log | 55.0 | 220 | 3.6862 |
102
+ | No log | 56.0 | 224 | 3.6334 |
103
+ | No log | 57.0 | 228 | 4.0924 |
104
+ | No log | 58.0 | 232 | 3.6489 |
105
+ | No log | 59.0 | 236 | 3.6355 |
106
+ | No log | 60.0 | 240 | 3.8356 |
107
+ | No log | 61.0 | 244 | 3.5758 |
108
+ | No log | 62.0 | 248 | 3.5889 |
109
+ | No log | 63.0 | 252 | 3.7572 |
110
+ | No log | 64.0 | 256 | 3.7237 |
111
+ | No log | 65.0 | 260 | 3.6545 |
112
+ | No log | 66.0 | 264 | 3.7671 |
113
+ | No log | 67.0 | 268 | 3.6976 |
114
+ | No log | 68.0 | 272 | 3.6523 |
115
+ | No log | 69.0 | 276 | 3.7270 |
116
+ | No log | 70.0 | 280 | 3.7120 |
117
+ | No log | 71.0 | 284 | 3.6896 |
118
+ | No log | 72.0 | 288 | 3.6892 |
119
+ | No log | 73.0 | 292 | 3.6871 |
120
+ | No log | 74.0 | 296 | 3.7154 |
121
+ | No log | 75.0 | 300 | 3.6874 |
122
+ | No log | 76.0 | 304 | 3.7207 |
123
+ | No log | 77.0 | 308 | 3.7025 |
124
+ | No log | 78.0 | 312 | 3.6979 |
125
+ | No log | 79.0 | 316 | 3.7120 |
126
+ | No log | 80.0 | 320 | 3.7363 |
127
+ | No log | 81.0 | 324 | 3.7563 |
128
+ | No log | 82.0 | 328 | 3.7290 |
129
+ | No log | 83.0 | 332 | 3.6939 |
130
+ | No log | 84.0 | 336 | 3.6881 |
131
+ | No log | 85.0 | 340 | 3.6798 |
132
+ | No log | 86.0 | 344 | 3.6658 |
133
+ | No log | 87.0 | 348 | 3.6642 |
134
+ | No log | 88.0 | 352 | 3.6678 |
135
+ | No log | 89.0 | 356 | 3.6846 |
136
+ | No log | 90.0 | 360 | 3.6806 |
137
+ | No log | 91.0 | 364 | 3.6778 |
138
+ | No log | 92.0 | 368 | 3.6777 |
139
+ | No log | 93.0 | 372 | 3.6907 |
140
+ | No log | 94.0 | 376 | 3.7072 |
141
+ | No log | 95.0 | 380 | 3.7095 |
142
+ | No log | 96.0 | 384 | 3.7103 |
143
+ | No log | 97.0 | 388 | 3.7127 |
144
+ | No log | 98.0 | 392 | 3.7138 |
145
+ | No log | 99.0 | 396 | 3.7140 |
146
+ | No log | 100.0 | 400 | 3.7135 |
147
+
148
+
149
+ ### Framework versions
150
+
151
+ - Transformers 4.36.2
152
+ - Pytorch 2.1.2+cu121
153
+ - Datasets 2.14.7
154
+ - Tokenizers 0.15.0
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/ltstorage/shares/datasets/glllm/data/finetuning/QA/GQA_RoBERTa",
3
+ "architectures": [
4
+ "RobertaForQuestionAnswering"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 514,
17
+ "model_type": "roberta",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 12,
20
+ "pad_token_id": 1,
21
+ "position_embedding_type": "absolute",
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.36.2",
24
+ "type_vocab_size": 1,
25
+ "use_cache": true,
26
+ "vocab_size": 50265
27
+ }
emissions.csv ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ timestamp,project_name,run_id,duration,emissions,emissions_rate,cpu_power,gpu_power,ram_power,cpu_energy,gpu_energy,ram_energy,energy_consumed,country_name,country_iso_code,region,cloud_provider,cloud_region,os,python_version,codecarbon_version,cpu_count,cpu_model,gpu_count,gpu_model,longitude,latitude,ram_total_size,tracking_mode,on_cloud,pue
2
+ 2024-03-06T02:07:47,codecarbon,02542dce-bdba-4f31-85d0-5194e105be25,365.8052337169647,0.05509155811839527,0.0001506035262497676,112.5,1012.4649999999999,377.88994789123535,0.01143122994154692,0.10571746573068545,0.03833793951150217,0.15548663518373454,Germany,DEU,free and hanseatic city of hamburg,,,Linux-6.5.0-21-generic-x86_64-with-glibc2.35,3.11.4,2.2.3,128,AMD EPYC 7543 32-Core Processor,4,4 x NVIDIA A40,9.9683,53.5649,1007.7065277099609,machine,N,1.0
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acb5fe237a39d7e1f98cda6112d1aaead203270ee25ab9edf8c0adb5c2c1748b
3
+ size 496250232
runs/Mar06_02-01-35_hcdsgpu2/events.out.tfevents.1709690501.hcdsgpu2.586318.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:384d671932ee757ababe9375a4ed65e0cbb3f454ab3d2f85965b58e599137038
3
+ size 32003
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "mask_token": "<mask>",
51
+ "max_length": 512,
52
+ "model_max_length": 1000000000000000019884624838656,
53
+ "pad_to_multiple_of": null,
54
+ "pad_token": "<pad>",
55
+ "pad_token_type_id": 0,
56
+ "padding_side": "right",
57
+ "sep_token": "</s>",
58
+ "stride": 0,
59
+ "tokenizer_class": "RobertaTokenizer",
60
+ "trim_offsets": true,
61
+ "truncation_side": "right",
62
+ "truncation_strategy": "only_second",
63
+ "unk_token": "<unk>"
64
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f46875f55804acdc8a2343701e96e8ad3621486a05def21003dec09862233c6
3
+ size 4920
vocab.json ADDED
The diff for this file is too large to render. See raw diff